Benchmarking Traditional ML Approaches in Phishing URL Detection

View Sample PDF

Author(s): T. S. Sangeetha (College of Engineering, Thiruvananthapuram, India), Keerthi Jayan (SRM Institute of Science and Technology, Kattankulathur, India), Sreya John (Kristu Jayanti University, India), D. Vetriselvi (SRM Institute of Science and Technology, India), G. L. Swathi Mirthika (SRM Institute of Science and Technology, India), Nisha Thorakkattu Thorakattil Madathil (UAE University, UAE)and K. S. Jishnu (SRM Institute of Science and Technology, Kattankulathur, India)
Copyright: 2026
Pages: 30
Source title: Navigating Public Security in the Age of Post-Truth: Challenges and Implications
Source Author(s)/Editor(s): Onur Ağırdil (Turkish National Police Academy, Turkey)and Ufuk Ayhan (Turkish National Police Academy, Turkey)
DOI: 10.4018/979-8-3373-6786-6.ch010

Keywords: Cyber and Network Security / Information Science Reference / Information Trust / Security & Forensics

Purchase

View Benchmarking Traditional ML Approaches in Phishing URL Detection on the publisher's website for pricing and purchasing information.

Abstract

Phishing attacks continue to pose a major cybersecurity challenge by exploiting deceptive URLs to obtain sensitive information. Although deep learning approaches such as CNNs, RNNs, and Transformers have demonstrated state of the art detection performance, traditional machine learning classifiers remain widely utilized because of their efficiency,interpretability, and relatively low resource requirements. In this study, we implement and evaluate ten machine learning models including Logistic Regression, Gradient Boosting, CatBoost, XGBoost, and Multi-Layer Perceptron on a publicly available phishing URL dataset from Kaggle. Experimental results show that ensemble based models,particularly XGBoost and Random Forest, achieve the highest accuracy, while Logistic Regression offers competitive performance with the advantages of simplicity, interpretability, and low computational overhead. The findings highlight the tradeoffs between accuracy, interpretability, and computational cost,providing practical guidance for selecting appropriate models in real world phishing detection systems.

The IRMA Community

Research IRM

Benchmarking Traditional ML Approaches in Phishing URL Detection

Purchase

Abstract

Related Content

IRMA Sponsors